wav2vec2-attempt2

README.md

@@ -3,6 +3,9 @@ license: apache-2.0
 base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
 - name: wav2vec2-attempt2
   results: []
@@ -15,14 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.1281
-- eval_accuracy: 0.0444
-- eval_f1: 0.0042
-- eval_runtime: 4.9552
-- eval_samples_per_second: 9.081
-- eval_steps_per_second: 1.009
-- epoch: 4.8
-- step: 10
+- Loss: 3.1319
+- Accuracy: 0.0667
+- F1: 0.0121
 
 ## Model description
 
@@ -53,6 +51,18 @@ The following hyperparameters were used during training:
 - num_epochs: 6
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.96  | 2    | 3.1337          | 0.0444   | 0.0066 |
+| No log        | 1.92  | 4    | 3.1337          | 0.0444   | 0.0066 |
+| No log        | 2.88  | 6    | 3.1341          | 0.0444   | 0.0128 |
+| No log        | 3.84  | 8    | 3.1299          | 0.0444   | 0.0043 |
+| 3.1206        | 4.8   | 10   | 3.1281          | 0.0444   | 0.0042 |
+| 3.1206        | 5.76  | 12   | 3.1319          | 0.0667   | 0.0121 |
+
+
 ### Framework versions
 
 - Transformers 4.36.2

runs/May01_22-10-00_ip-10-0-2-237/events.out.tfevents.1714601401.ip-10-0-2-237.5033.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce049e5d2fb1aa61d0b2de9f5c2852e9dea0688319abcefd42c69137bae679c9
-size 8790
+oid sha256:35e0eb5d0c2d576548998200a908d07f57366df1d381a88c458cf4396eb353c5
+size 9500